DI-UMONS : Dépôt institutionnel de l’université de Mons

Recherche transversale
(titres de publication, de périodique et noms de colloque inclus)
2017-07-19 - Colloque/Présentation - poster - Anglais - 1 page(s)

Rahouti Anass , Ruggiero Lovreglio, Charita Dias, Datoussaïd Sélim , "Simulating Assisted Evacuation using Unity3D" in Traffic & Granular Flow, Washington, USA, 2017

  • Codes CREF : Intelligence artificielle (DI1180), Processus stochastiques (DI1131), Théorie de la décision et des jeux (DI1134)
  • Unités de recherche UMONS : Génie civil et Mécanique des Structures (F801)
  • Instituts UMONS : Institut des Sciences et du Management des Risques (Risques)
Texte intégral :

Abstract(s) :

(Anglais) Past studies on emergency events have revealed that occupants’ behaviours and capabilities, procedural aspects, and environmental constraints affect the evacuation performance of healthcare facilities. In addition to complying with prescriptive/performance-based codes and standards, healthcare facilities management needs to consider the occupants’ abilities and needs and the unique layout of the healthcare environments to design occupant-centric egress systems. At any time, a healthcare facility may contain a wide variety of occupants with different roles (e.g. visitors, staff members and patients), different knowledge of the facility layout, and varying physical, mental and ambulatory abilities. In such environments, occupants can be divided in three categories: Independent, their mobility is not impaired in any way and they are able to physically leave the premises without any (or with minimum) assistance; Dependent, all occupants except those defined as independent; Highly-dependent, those occupants whose clinical treatment and/or condition create a high-dependency on other people. Dependent and Highly-dependent occupants should be assisted by others during the evacuation process. Different transportation devices are available in the market and could be used to move the patients from the dangerous area to a safer one (wheelchair, hospital bed, carry chair, evacuation chair, stretcher, rescue sheet). Therefore, assisted evacuation sub-model can be considered as a fundamental feature in evacuation modelling tools to estimate egress times in healthcare facilities. There exist over 60 evacuation models but only few of them (e.g. buildingEXODUS [1] and Pathfinder [2]) are able to simulate assisted evacuation. This paper presents a proof of concept showing that game engines as Unity3D [3] can be useful tools to develop such sub-model based on the artificial intelligence of autonomous agents.